Surface defect inspection plays an important role in the process of industrial manufacture and production. Though Convolutional Neural Network (CNN) based defect inspection methods have made huge leaps, they still confront a lot of challenges such as defect scale variation, complex background, low contrast, and so on. To address these issues, we propose a joint attention-guided feature fusion network (JAFFNet) for saliency detection of surface defects based on the encoder-decoder network. JAFFNet mainly incorporates a joint attention-guided feature fusion (JAFF) module into decoding stages to adaptively fuse low-level and high-level features. The JAFF module learns to emphasize defect features and suppress background noise during feature fusion, which is beneficial for detecting low-contrast defects. In addition, JAFFNet introduces a dense receptive field (DRF) module following the encoder to capture features with rich context information, which helps detect defects of different scales. The JAFF module mainly utilizes a learned joint channel-spatial attention map provided by high-level semantic features to guide feature fusion. The attention map makes the model pay more attention to defect features. The DRF module utilizes a sequence of multi-receptive-field (MRF) units with each taking as inputs all the preceding MRF feature maps and the original input. The obtained DRF features capture rich context information with a large range of receptive fields. Extensive experiments conducted on SD-saliency-900, Magnetic tile, and DAGM 2007 indicate that our method achieves promising performance in comparison with other state-of-the-art methods. Meanwhile, our method reaches a real-time defect detection speed of 66 FPS.

With the globalisation of manufacturing industry, extendable and networked computer numerical control systems that can support bidirectional and seamless data exchange are in urgent need. This paper presents a STEP-NC compliant controller based on Real-time Ethernet technologies, which consists of functional modules such as General Interpreter, Machining Manager, Tool Path Generation, Machine Tool Model, Simulation and Real-Time Ethernet Interface. The proposed controller is implemented for circuit board milling. In the controller, STEP-NC is utilised as the data format, as well as a part of the controller's software structure. The late binding together with object oriented polymorphism and iteration, which can accomplish general functions, is used in developing the interpreter. This, together with the Reflection mechanism, also realises the general function of creating and modifying some of the STEP data. This controller is then tested on a circuit board milling machine, with ISO 14649 files generated by a CAM module developed in association with this work, in which some AP210 entities are added to represent circuits’ geometry and translated to machining features in the STEP-NC format. Moreover, machining a single feature with multi tools is discussed and the concept of final features is adopted; all contribute to some effective milling strategies.

Training deep neural networks typically relies on gradient descent learning schemes, which is usually time-consuming, and the design of complex network architectures is often intractable. In this article, we explore the building of multilayer neural networks based on an efficient gradient-free learning scheme offering a potential solution to the architectural design. The proposed learning scheme encompasses both forward and backward training (BT) processes. In the forward process, the pseudoinverse learning (PIL) algorithm is employed to train a multilayer neural network, in which the network is dynamically constructed leveraging a layer-by-layer greedy strategy, enabling the automatic determination of the architecture across different hierarchies in a data-driven manner. The network architecture and connection weights determined in the forward training (FT) process are shared with the backward process which also conducts gradient-free learning to update the connection weights. After the bidirectional learning, a neural network comprising two twin subnetworks is obtained, and the fused features of subnetworks are used as inputs for downstream tasks. Comprehensive experiments and detailed analyses demonstrate the effectiveness and superiority of the proposed learning scheme.